Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add autohandai/community-skills --skill code-reviewgit clone --depth 1 https://github.com/autohandai/community-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/autohandai/community-skills/code-review)<a href="https://agentmods.dev/skills/autohandai/community-skills/code-review"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/autohandai/community-skills/code-review"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.02173 |
| Opus 5 | $0.00024 | $0.01086 |
| Sonnet 5 | $0.00010 | $0.00435 |
| Haiku 4.5 | $0.00005 | $0.00217 |
Grade A, and why
code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
95% identical to code-review — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 393 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
When to use this skill
- Reviewing pull requests
- Checking code quality
- Providing feedback on implementations
- Identifying potential bugs
- Suggesting improvements
- Security audits
- Performance analysis
Instructions
Step 1: Understand the context
Read the PR description:
- What is the goal of this change?
- Which issues does it address?
- Are there any special considerations?
Check the scope:
- How many files changed?
- What type of changes? (feature, bugfix, refactor)
- Are tests included?
Step 2: High-level review
Architecture and design:
- Does the approach make sense?
- Is it consistent with existing patterns?
- Are there simpler alternatives?
- Is the code in the right place?
Code organization:
- Clear separation of concerns?
- Appropriate abstraction levels?
- Logical file/folder structure?
Step 3: Detailed code review
Naming:
- Variables: descriptive, meaningful names
- Functions: verb-based, clear purpose
- Classes: noun-based, single responsibility
- Constants: UPPER_CASE for true constants
- Avoid abbreviations unless widely known
Functions:
- Single responsibility
- Reasonable length (< 50 lines ideally)
- Clear inputs and outputs
- Minimal side effects
- Proper error handling
Classes and objects:
- Single responsibility principle
- Open/closed principle
- Liskov substitution principle
- Interface segregation
- Dependency inversion
Error handling:
- All errors caught and handled
- Meaningful error messages
- Proper logging
- No silent failures
- User-friendly errors for UI
Code quality:
- No code duplication (DRY)
- No dead code
- No commented-out code
- No magic numbers
- Consistent formatting
Step 4: Security review
Input validation:
- All user inputs validated
- Type checking
- Range checking
- Format validation
Authentication & Authorization:
- Proper authentication checks
- Authorization for sensitive operations
- Session management
- Password handling (hashing, salting)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 393 lines · 49 tokens per session scan A 95b1d9c73416
code-review is a skill published in the GitHub repository autohandai/community-skills (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 2,173 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to code-review, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
simplify-code
Sequential 3-lens cleanup of recent code changes.
agentic-review
Use when reviewing current branch for bugs before pushing or merging, when wanting a thorough multi-agent review of local changes, or when preparing work for human review. Not for codebase structure, not for code style, and not for fixing what it finds.
codespaces
Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal…
ai-slop-cleaner
Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.
the-council
Multi-model advisory board using Qwen through OpenRouter and Google Gemini by default, with OpenAI Codex available as an explicit or compatibility-fallback seat. Invoke when the user requests a "council" review, wants a second opinion from other AI models, asks for multi-model consensus, or says "ask the council".…
hqe
Comprehensive codebase health auditing, remediation, and verification skill based on the canonical HQE Protocol v5.0.0.